Process knowledge-based random forest regression for model predictive control on a nonlinear production process with multiple working conditions |
| |
| Affiliation: | 1. College of Civil Engineering, Central South University, Changsha 410075, China;2. State Key Laboratory of High Performance Complex Manufacturing, Central South University, Changsha 410083, China;3. China Railway Construction Heavy Industry Co. Ltd, Changsha 410100, China;4. Key Laboratory of Shield Tunneling and Tunneling Tool Technology in Jilin Province, Jilin Welter Tunnel Equipment Co., Ltd, Jilin 132299, China;1. School of Mechanical Engineering, Sichuan University, Chengdu 610065, China;2. Yibin Industrial Technology Research Institute of Sichuan University, Yibin 644000, China;3. Chengdu Yigao Intelligent Technology Co., Ltd., Chengdu 610065, China;1. Technische Universität Berlin, Germany;2. Hermann-Rietschel-Institut, Technische Universität Berlin, Berlin Germany;3. Leibniz University Hannover, Germany;1. School of Mechanical Engineering, Yanshan University, Qinhuangdao City, Hebei, PR China;2. Department of Mechanical Engineering, University of Manitoba, Winnipeg, MB, Canada;1. Department of Mechanical and Industrial Engineering, University of Illinois at Chicago, Chicago, IL 60607, USA;2. School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, China;3. School of Business, Jilin University, Changchun 130012, China |
| |
| Abstract: | In process industry, predictive control approaches have been widely used for nonlinear production processes. Practically, the predictor in a predictive controller is extremely important since it provides future states for the optimization problem of controllers. The conventional predictive controller with precise mathematical predictors approximating the state space of physical systems is difficult and time-consuming for nonlinear production processes, and it performs poorly over a wide range of working conditions and with significant disturbances. To address the challenges, the trend of applying artificial intelligence emerges. However, the industrial process-specific knowledge is ignored in most cases. In this study, a predictive controller with a control process knowledge-based random forest (RF) model is proposed. Specifically, working data are clustered at first to handle diverse working conditions. Then, a process knowledge-based forest predictor, namely MIW-RF model with a redesigned cascading RF structure, is proposed to incorporate control process knowledge into modeling. Thus, future states of controlled variables could be more accurately acquired for the optimizer. A simplified version of the predictive model is also developed with quick model training and updating. The proposed predictive methods are finally introduced into the controller design. According to the empirical results, the proposed methods deliver a better control performance against benchmarks, including more accurate anticipated controlled-variable responses, better set-point tracking and disturbance rejection capability. |
| |
| Keywords: | Model predictive control Knowledge-based random forest Nonlinear process Process industry |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
